© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38925
    Prev
    Next
    INDEX
    Explanations

    This is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zako
    -1.31
     zespołu
    -1.22
     Tamaño
    -1.21
     (!__
    -1.18
     Tamanho
    -1.16
     szczeg
    -1.12
    ottes
    -1.12
     asegurarse
    -1.11
     mercancías
    -1.10
     dodat
    -1.09
    POSITIVE LOGITS
     is
    2.13
     this
    2.11
     This
    1.69
     это
    1.62
     هذا
    1.59
    This
    1.51
     این
    1.48
     này
    1.48
     هذه
    1.43
    นี้
    1.39
    Activations Density 0.022%

    No Known Activations